rememberstack 0.1.0__tar.gz → 0.2.0__tar.gz

rememberstack-0.2.0/.env.example

@@ -0,0 +1,59 @@
+# Local-only quickstart credentials. Replace every secret before exposing the stack.
+REMEMBERSTACK_POSTGRES_USER=rememberstack
+REMEMBERSTACK_POSTGRES_PASSWORD=rememberstack-local-only
+REMEMBERSTACK_POSTGRES_DB=rememberstack
+REMEMBERSTACK_MINIO_ACCESS_KEY=rememberstack-local
+REMEMBERSTACK_MINIO_SECRET_KEY=rememberstack-local-only
+
+# One stable deployment identity; changing it creates a different trust domain.
+REMEMBERSTACK_SELFHOST_DEPLOYMENT_ID=11111111-1111-4111-8111-111111111111
+REMEMBERSTACK_SELFHOST_DEPLOYMENT_SLUG=local
+REMEMBERSTACK_SELFHOST_DEPLOYMENT_NAME=Local memory
+REMEMBERSTACK_SELFHOST_API_PORT=8000
+# Where clients and the benchmark CLI look for that API. It defaults to
+# http://127.0.0.1:8000 independently of the port above, so if you change
+# REMEMBERSTACK_SELFHOST_API_PORT you must set this too or every client call
+# fails with "Connection refused" against the old port.
+# REMEMBERSTACK_API_URL=http://127.0.0.1:8000
+
+# Required to start the provider adapter. Replace this value before processing
+# a corpus; the complete Compose pipeline makes extraction and embedding calls.
+REMEMBERSTACK_OPENROUTER_API_KEY=replace-before-real-use
+# Optional exact OpenRouter embedding-provider slug; unset keeps automatic routing.
+# REMEMBERSTACK_OPENROUTER_EMBEDDING_PROVIDER=nebius
+# 32k covers reasoning plus content; the provider account cap remains the monetary boundary.
+REMEMBERSTACK_OPENROUTER_MAX_COMPLETION_TOKENS=32000
+# Optional global reasoning effort for every chat-generation call. Allowed:
+# none, minimal, low, medium, high, xhigh, max. Unset uses the model default;
+# "none" reduces extraction latency but can reduce adjudication quality, and
+# models that require reasoning may reject it.
+# REMEMBERSTACK_OPENROUTER_REASONING_EFFORT=none
+# Optional per-model overrides as a JSON object of model-id → effort. A model's
+# entry wins over the global pin above; models absent from the map fall back to
+# the global pin (or the model default when that is also unset). Same allowed
+# effort literals. Example: pin flash models to none while keeping high for a
+# reasoning model.
+# REMEMBERSTACK_OPENROUTER_REASONING_EFFORT_MAP={"z-ai/glm-4.7-flash":"none","openai/gpt-5.6-luna":"high"}
+
+# OBSERVABILITY (optional; empty or unset keeps all exporters disabled).
+# Sentry-protocol error tracking works with Sentry, GlitchTip, and Bugsink.
+# The environment defaults to REMEMBERSTACK_SELFHOST_DEPLOYMENT_SLUG and the
+# error-event sample rate defaults to 1.0.
+# REMEMBERSTACK_SENTRY_DSN=
+# REMEMBERSTACK_SENTRY_ENVIRONMENT=
+# REMEMBERSTACK_SENTRY_SAMPLE_RATE=1.0
+# LoCoMo answer/judge tracing activates only when all three values are non-empty.
+# LANGFUSE_PUBLIC_KEY=
+# LANGFUSE_SECRET_KEY=
+# LANGFUSE_HOST=https://cloud.langfuse.com
+
+# Optional benchmark/deployment model overrides. Keep explicit model IDs for a
+# reproducible run; do not use a rotating router such as openrouter/free.
+# REMEMBERSTACK_E2_EXTRACT_MODEL=nvidia/nemotron-3-super-120b-a12b:free
+# REMEMBERSTACK_E3_NORMALIZE_MODEL=nvidia/nemotron-3-super-120b-a12b:free
+# D79 structure seats: STRUCTURER names only the string-anchor fallback
+# proposer; the routine skeleton path is deterministic and calls no model.
+# REMEMBERSTACK_STRUCTURER_MODEL=openai/gpt-5.6-luna
+# REMEMBERSTACK_SKELETON_CHECK_MODEL=z-ai/glm-4.7-flash
+# REMEMBERSTACK_ROLE_MODEL=z-ai/glm-4.7-flash
+# REMEMBERSTACK_SUMMARY_MODEL=z-ai/glm-4.7-flash

{rememberstack-0.1.0 → rememberstack-0.2.0}/.github/workflows/ci.yml

@@ -18,6 +18,9 @@ jobs:
       contents: read
     env:
       QUICKSTART_TARGET_SECONDS: "600"
+      # Stamped into the built image so provenance checks have something true to
+      # compare against; see plan/designs/locomo_benchmark_design.md.
+      REMEMBERSTACK_BUILD_REVISION: ${{ github.sha }}
     steps:
       - uses: actions/checkout@v4
 
@@ -29,6 +32,11 @@ jobs:
           started_at="$(date +%s)"
           docker compose --env-file .env.example up --build --detach --wait
           curl --fail http://localhost:8000/recipes
+          # A dropped build-arg would otherwise stay green until a real
+          # benchmark answer stage refused to run.
+          served_revision="$(curl --fail --silent http://localhost:8000/deployment \
+            | python3 -c 'import json,sys; print(json.load(sys.stdin)["build_revision"])')"
+          test "$served_revision" = "${REMEMBERSTACK_BUILD_REVISION}"
           elapsed_seconds="$(($(date +%s) - started_at))"
           echo "Quickstart cold start to first query: ${elapsed_seconds}s / ${QUICKSTART_TARGET_SECONDS}s target" \
             | tee -a "$GITHUB_STEP_SUMMARY"
@@ -53,28 +61,60 @@ jobs:
               raise RuntimeError("MinIO replaced an immutable object key")
           PY
 
-      - name: Ingest and observe the E0 chain
+      - name: Prove the zero-cost full pipeline
         run: |
-          curl --fail --data-binary $'# Hello\n\nCompose smoke.\n' \
-            'http://localhost:8000/ingest?filename=smoke.md&mime=text%2Fmarkdown'
+          running_services="$(
+            docker compose --env-file .env.example ps --status running --services
+          )"
+          for service in \
+            api worker-convert worker-structure worker-chunk worker-embed-chunk \
+            worker-extract-claims worker-normalize-relations \
+            worker-adjudicate-supersession worker-embed-claim worker-reconcile \
+            worker-label-relation; do
+            printf '%s\n' "$running_services" | grep -qx "$service"
+          done
+          ingested="$(
+            curl --fail --header 'Content-Type: application/octet-stream' \
+              --data-binary ' ' \
+              'http://localhost:8000/ingest?filename=empty.md&mime=text%2Fmarkdown'
+          )"
+          version_id="$(
+            printf '%s' "$ingested" |
+              docker compose --env-file .env.example exec -T api \
+                python -c 'import json, sys; print(json.load(sys.stdin)["version_id"])'
+          )"
           observed=''
-          for attempt in {1..30}; do
+          for attempt in {1..60}; do
             observed="$(docker compose --env-file .env.example exec -T postgres \
               psql -U rememberstack -d rememberstack -Atc \
-              "SELECT count(*) FILTER (WHERE stage='convert' AND status='succeeded'), count(*) FILTER (WHERE stage='structure' AND status='succeeded'), count(*) FILTER (WHERE stage='chunk' AND status='pending') FROM processing_state")"
-            if [ "$observed" = '1|1|1' ]; then
+              "SELECT count(*), count(*) FILTER (WHERE status='succeeded'), count(DISTINCT stage) FROM processing_state WHERE target_id='$version_id'")"
+            if [ "$observed" = '10|10|10' ]; then
               break
             fi
             sleep 1
           done
-          test "$observed" = '1|1|1'
+          test "$observed" = '10|10|10'
           test "$(docker compose --env-file .env.example exec -T postgres \
-            psql -U rememberstack -d rememberstack -Atc 'SELECT count(*) FROM cost_ledger')" = '0'
+            psql -U rememberstack -d rememberstack -Atc \
+            'SELECT count(*) FROM cost_ledger')" = '0'
+          docker compose --env-file .env.example --profile operations \
+            run --rm projections
+          readiness="$(
+            curl --fail --header 'Content-Type: application/json' \
+              --data "[\"$version_id\"]" \
+              'http://localhost:8000/readiness?require_projections=true'
+          )"
+          printf '%s' "$readiness" |
+            docker compose --env-file .env.example exec -T api python -c \
+              'import json, sys; report = json.load(sys.stdin); assert report["ready"]; assert all(item["ready"] for item in report["projections"])'
 
       - name: Stage an upgrade from the prior schema
         run: |
           docker compose --env-file .env.example stop \
-            api worker-convert worker-structure
+            api worker-convert worker-structure worker-chunk worker-embed-chunk \
+            worker-extract-claims worker-normalize-relations \
+            worker-adjudicate-supersession worker-embed-claim worker-reconcile \
+            worker-label-relation
           docker compose --env-file .env.example run --rm --no-deps \
             --entrypoint alembic setup downgrade p7_02_0016
           test "$(docker compose --env-file .env.example exec -T postgres \
@@ -116,7 +156,7 @@ jobs:
             docker compose "${compose_args[@]}" ps --status running --services
           )"
           test -z "$(printf '%s\n' "$running_services" \
-            | grep -E '^(api|worker-convert|worker-structure)$' || true)"
+            | grep -E '^(api|worker-(convert|structure|chunk|embed-chunk|extract-claims|normalize-relations|adjudicate-supersession|embed-claim|reconcile|label-relation))$' || true)"
           test "$(docker compose "${compose_args[@]}" exec -T postgres \
             psql -U rememberstack -d rememberstack -Atc \
             'SELECT version_num FROM alembic_version')" = 'p7_02_0016'
@@ -126,14 +166,18 @@ jobs:
           trap - EXIT
           test "$(docker compose --env-file .env.example exec -T postgres \
             psql -U rememberstack -d rememberstack -Atc \
-            'SELECT version_num FROM alembic_version')" = 'p7_05_0017'
+            'SELECT version_num FROM alembic_version')" = 'p1_04_0019'
           test "$(docker compose --env-file .env.example exec -T postgres \
             psql -U rememberstack -d rememberstack -Atc \
             'SELECT count(*) FROM deployments')" = '1'
           running_services="$(
             docker compose "${compose_args[@]}" ps --status running --services
           )"
-          for service in api worker-convert worker-structure; do
+          for service in \
+            api worker-convert worker-structure worker-chunk worker-embed-chunk \
+            worker-extract-claims worker-normalize-relations \
+            worker-adjudicate-supersession worker-embed-claim worker-reconcile \
+            worker-label-relation; do
             printf '%s\n' "$running_services" | grep -qx "$service"
           done
           curl --fail http://localhost:8000/healthz
@@ -189,13 +233,13 @@ jobs:
         run: uv run lint-imports
 
       - name: Ruff lint
-        run: uv run ruff check src/
+        run: uv run ruff check src/ benchmarks/
 
       - name: Ruff format check
-        run: uv run ruff format --check src/
+        run: uv run ruff format --check src/ benchmarks/
 
       - name: Pyright type check
-        run: uv run pyright src/ --pythonversion ${{ matrix.python-version }}
+        run: uv run pyright src/ benchmarks/ --pythonversion ${{ matrix.python-version }}
 
       - name: Real PostgreSQL Alembic lifecycle
         run: uv run pytest src/tests/spine/test_migrations.py -v --tb=short

{rememberstack-0.1.0 → rememberstack-0.2.0}/.github/workflows/release.yml

@@ -48,9 +48,9 @@ jobs:
       - name: Verify architecture, style, and types
         run: |
           uv run lint-imports
-          uv run ruff check src/
-          uv run ruff format --check src/
-          uv run pyright src/ --pythonversion 3.14
+          uv run ruff check src/ benchmarks/
+          uv run ruff format --check src/ benchmarks/
+          uv run pyright src/ benchmarks/ --pythonversion 3.14
 
       - name: Run the release test suite
         run: uv run pytest src/tests -q
@@ -116,6 +116,8 @@ jobs:
           push: true
           tags: ${{ steps.metadata.outputs.tags }}
           labels: ${{ steps.metadata.outputs.labels }}
+          build-args: |
+            REMEMBERSTACK_BUILD_REVISION=${{ github.sha }}
 
   github-release:
     name: Publish GitHub release

{rememberstack-0.1.0 → rememberstack-0.2.0}/.gitignore

@@ -20,3 +20,4 @@ htmlcov/
 .loopy_loop/state.json.lock
 .loopy_loop/state.json.archive_*.json
 .eval-banana/results/
+.benchmark-runs/